{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NCTMZTG4ELO2X5XKFNLZ66NDNX","short_pith_number":"pith:NCTMZTG4","canonical_record":{"source":{"id":"2606.04284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T23:19:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8fcab7f340a77168d87e02ca70caf842d3bfa0bb7c466d10b4d7e24f243461a8","abstract_canon_sha256":"597def73a0fb4974fe3c38678c928e1c94625e63a514933a407798daa6b020d9"},"schema_version":"1.0"},"canonical_sha256":"68a6ccccdc22ddabf6ea2b579f79a36dec4bd91ea43994e497b73fd028980578","source":{"kind":"arxiv","id":"2606.04284","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04284","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04284v1","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04284","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"NCTMZTG4ELO2","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"NCTMZTG4ELO2X5XK","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"NCTMZTG4","created_at":"2026-06-04T01:09:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NCTMZTG4ELO2X5XKFNLZ66NDNX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T23:19:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8fcab7f340a77168d87e02ca70caf842d3bfa0bb7c466d10b4d7e24f243461a8","abstract_canon_sha256":"597def73a0fb4974fe3c38678c928e1c94625e63a514933a407798daa6b020d9"},"schema_version":"1.0"},"canonical_sha256":"68a6ccccdc22ddabf6ea2b579f79a36dec4bd91ea43994e497b73fd028980578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:02.019133Z","signature_b64":"C8iXchZb8YTbv9zoZldTZ8mV64dIRcmL7528VF1GSMbI/CKfLP/rrIkEMHExfGVSTkgLluNtYxeRPPkhGxxgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68a6ccccdc22ddabf6ea2b579f79a36dec4bd91ea43994e497b73fd028980578","last_reissued_at":"2026-06-04T01:09:02.018670Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:02.018670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04284","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTOLx+Qf2V7qntujBdXCb33Iu2erps/+lqgwJbo7HX4DPjw+P4JYLjtuAm9AZEvnPFNVz/3Glbhlc9sWdQOrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T21:18:46.900372Z"},"content_sha256":"19f6248bce923db5e3d338e5efbb0db719a884ccbf31389aa58ce4fa0d2e76e7","schema_version":"1.0","event_id":"sha256:19f6248bce923db5e3d338e5efbb0db719a884ccbf31389aa58ce4fa0d2e76e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NCTMZTG4ELO2X5XKFNLZ66NDNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Isabel Valera, Jinyi Mu, Ji-Ung Lee, Mayank Jobanputra, Soyoung Oh, Vera Demberg, Yifan Wang, Yu Wang","submitted_at":"2026-06-02T23:19:12Z","abstract_excerpt":"Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with human values. However, most existing approaches assume a universal reward function, neglecting the diversity and heterogeneity of human preferences. To address this limitation without additional annotation costs, recent work has proposed learning multiple preference components from binary data and combining them to model individual preferences. Nevertheless, these components often fail to capture coherent and disentangled patterns, limiting their in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04284","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04284/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FRnFD4HEUbiOfdOPDYoUeIvfWv+uX342xcsCyVxaFJ1knaNqdVUT6ocq81ddk5YHKYjOsMB1/77jUbqzMNdSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T21:18:46.900762Z"},"content_sha256":"169bb6688a06ecea8598a6e10fbf21ee53260c3e7479077233031e149b950315","schema_version":"1.0","event_id":"sha256:169bb6688a06ecea8598a6e10fbf21ee53260c3e7479077233031e149b950315"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX/bundle.json","state_url":"https://pith.science/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-24T21:18:46Z","links":{"resolver":"https://pith.science/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX","bundle":"https://pith.science/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX/bundle.json","state":"https://pith.science/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCTMZTG4ELO2X5XKFNLZ66NDNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NCTMZTG4ELO2X5XKFNLZ66NDNX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"597def73a0fb4974fe3c38678c928e1c94625e63a514933a407798daa6b020d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T23:19:12Z","title_canon_sha256":"8fcab7f340a77168d87e02ca70caf842d3bfa0bb7c466d10b4d7e24f243461a8"},"schema_version":"1.0","source":{"id":"2606.04284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04284","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04284v1","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04284","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"NCTMZTG4ELO2","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"NCTMZTG4ELO2X5XK","created_at":"2026-06-04T01:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"NCTMZTG4","created_at":"2026-06-04T01:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:169bb6688a06ecea8598a6e10fbf21ee53260c3e7479077233031e149b950315","target":"graph","created_at":"2026-06-04T01:09:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.04284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with human values. However, most existing approaches assume a universal reward function, neglecting the diversity and heterogeneity of human preferences. To address this limitation without additional annotation costs, recent work has proposed learning multiple preference components from binary data and combining them to model individual preferences. Nevertheless, these components often fail to capture coherent and disentangled patterns, limiting their in","authors_text":"Isabel Valera, Jinyi Mu, Ji-Ung Lee, Mayank Jobanputra, Soyoung Oh, Vera Demberg, Yifan Wang, Yu Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T23:19:12Z","title":"Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04284","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:19f6248bce923db5e3d338e5efbb0db719a884ccbf31389aa58ce4fa0d2e76e7","target":"record","created_at":"2026-06-04T01:09:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"597def73a0fb4974fe3c38678c928e1c94625e63a514933a407798daa6b020d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T23:19:12Z","title_canon_sha256":"8fcab7f340a77168d87e02ca70caf842d3bfa0bb7c466d10b4d7e24f243461a8"},"schema_version":"1.0","source":{"id":"2606.04284","kind":"arxiv","version":1}},"canonical_sha256":"68a6ccccdc22ddabf6ea2b579f79a36dec4bd91ea43994e497b73fd028980578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68a6ccccdc22ddabf6ea2b579f79a36dec4bd91ea43994e497b73fd028980578","first_computed_at":"2026-06-04T01:09:02.018670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:02.018670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C8iXchZb8YTbv9zoZldTZ8mV64dIRcmL7528VF1GSMbI/CKfLP/rrIkEMHExfGVSTkgLluNtYxeRPPkhGxxgAg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:02.019133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19f6248bce923db5e3d338e5efbb0db719a884ccbf31389aa58ce4fa0d2e76e7","sha256:169bb6688a06ecea8598a6e10fbf21ee53260c3e7479077233031e149b950315"],"state_sha256":"12bac9281fbacf7a045922390e9deeff3a96a62780eedc52271e5ce23afeae0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkxkQsmJDWvzBrwZwOs7o5kJG8Cm35Im6YCURvZs3LzRwrSuRBeYNIhuBsW+aQKMTqftWUHsdcNtN5MBGsi1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T21:18:46.902823Z","bundle_sha256":"8d816820d6d6bcb687fabe5b46fb6220b7ebeea6fca2015f7f21b5dc6fc93415"}}